FCL-Net: Towards accurate edge detection via Fine-scale Corrective Learning

Integrating multi-scale predictions has become a mainstream paradigm in edge detection. However, most existing methods mainly focus on effective feature extraction and multi-scale feature fusion while ignoring the low learning capacity in fine-level branches, limiting the overall fusion performance....

Full description

Saved in:
Bibliographic Details
Published in:Neural networks 2022-01, Vol.145, p.248-259
Main Authors: Xuan, Wenjie, Huang, Shaoli, Liu, Juhua, Du, Bo
Format: Article
Language:English
Subjects:
Cues
Edge detection
Fine-scale Corrective Learning
Image Processing, Computer-Assisted
Neural Networks, Computer
Pixel-level fusion
Semantics
Top-down attentional guidance
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Integrating multi-scale predictions has become a mainstream paradigm in edge detection. However, most existing methods mainly focus on effective feature extraction and multi-scale feature fusion while ignoring the low learning capacity in fine-level branches, limiting the overall fusion performance. In light of this, we propose a novel Fine-scale Corrective Learning Net (FCL-Net) that exploits semantic information from deep layers to facilitate fine-scale feature learning. FCL-Net mainly consists of a Top-down Attentional Guiding (TAG) and a Pixel-level Weighting (PW) module. TAG module adopts semantic attentional cues from coarse-scale prediction into guiding the fine-scale branches by learning a top-down LSTM. PW module treats the contribution of each spatial location independently and promote fine-level branches to detect detailed edges with high confidence. Experiments on three benchmark datasets, i.e., BSDS500, Multicue, and BIPED, show that our approach significantly outperforms the baseline and achieves a competitive ODS F-measure of 0.826 on the BSDS500 benchmark. The source code and models are publicly available at https://github.com/DREAMXFAR/FCL-Net.
ISSN:0893-6080
1879-2782
DOI:10.1016/j.neunet.2021.10.022